© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159984
    Prev
    Next
    INDEX
    Explanations

    costs of consumers

    np_acts-logits-general · gemini-2.5-flash-lite

    describing sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    联合
    0.53
    澳门
    0.49
    里程
    0.47
     нарушение
    0.47
    几个
    0.46
    优化
    0.46
    🫢
    0.46
    四个
    0.46
    三个
    0.45
    的时候
    0.45
    POSITIVE LOGITS
    خ
    0.53
    s
    0.49
    англ
    0.48
     خ
    0.47
    ானி
    0.46
    h
    0.46
    oh
    0.46
    b
    0.46
     suele
    0.45
     schreibt
    0.45
    Activations Density 0.001%

    No Known Activations